Analysis of 3-D images of dental imprints using computer vision

Michele Aubin; Jean Cote; Denis Laurendeau; Denis Poussart

doi:10.1117/12.59363

6 May 1992 Analysis of 3-D images of dental imprints using computer vision

Michele Aubin, Jean Cote, Denis Laurendeau, Denis Poussart

Proceedings Volume 1641, Physiological Monitoring and Early Detection Diagnostic Methods; (1992) https://doi.org/10.1117/12.59363
Event: OE/LASE '92, 1992, Los Angeles, CA, United States

Abstract

This paper addressed two important aspects of dental analysis: (1) location and (2) identification of the types of teeth by means of 3-D image acquisition and segmentation. The 3-D images of both maxillaries are acquired using a wax wafer as support. The interstices between teeth are detected by non-linear filtering of the 3-D and grey-level data. Two operators are presented: one for the detection of the interstices between incisors, canines, and premolars and one for those between molars. Teeth are then identified by mapping the imprint under analysis on the computer model of an 'ideal' imprint. For the mapping to be valid, a set of three reference points is detected on the imprint. Then, the points are put in correspondence with similar points on the model. Two such points are chosen based on a least-squares fit of a second-order polynomial of the 3-D data in the area of canines. This area is of particular interest since the canines show a very characteristic shape and are easily detected on the imprint. The mapping technique is described in detail in the paper as well as pre-processing of the 3-D profiles. Experimental results are presented for different imprints.

Citation Download Citation

Michele Aubin, Jean Cote, Denis Laurendeau, and Denis Poussart "Analysis of 3-D images of dental imprints using computer vision", Proc. SPIE 1641, Physiological Monitoring and Early Detection Diagnostic Methods, (6 May 1992); https://doi.org/10.1117/12.59363

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available